Qi Diao

Dr. Qi Diao


Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
25 February 2024 in Baghdad Science Journal
Verified
Journal Article
Open access
PDF file
QDQi Diao
Qi Diao
AJApri Junaidi
Apri Junaidi
WCWeng Howe Chan
Weng Howe Chan
AZAzland Mohd Zain Zain
Azland Mohd Zain Zain
HYHao Long Yang
Hao Long Yang
تم تقديم طريقة تحسين إرشادية جديدة تعتمد على الإنسان، تسمى خوارزمية التحسين المستندة إلى السنوكر (SBOA)، في هذه الدراسة. الإلهام لهذه الطريقة مستوحى من سمات نخبة المبيعات - تلك الصفات التي يطمح كل مندوب مبيعات إلى امتلاكها. عادةً ما يسعى مندوبو المبيعات إلى تعزيز مهاراتهم من خلال التعلم الذاتي أو من خلال طلب التوجيه من الآخرين. علاوة على ذلك، فإنهم يشاركون في اتصالات منتظمة مع العملاء للحصول على الموافقة على منتجاتهم أو خدماتهم. بناءً على هذا المفهوم، تهدف SBOA إلى إيجاد الحل الأمثل ضمن مساحة بحث معينة، واجتياز جميع المواضع للحصول على جميع القيم الممكنة. لتقييم جدوى وفعالية SBOA مقارنة بالخوارزميات الأخرى، أجرينا اختبارات على عشر وظائف ذات هدف واحد من الوظائف المعيارية لعام 2019 للحساب التطوري (CEC)، بالإضافة إلى أربع وعشرين وظيفة ذات هدف واحد من CEC لعام 2022. وظائف مرجعية، بالإضافة إلى أربع مشاكل هندسية. تم استخدام سبع خوارزميات مقارنة: خوارزمية التطور التفاضلي (DE)، خوارزمية بحث العصفور (SSA)، خوارزمية جيب التمام (SCA)، خوارزمية تحسين الحيتان (WOA)، خوارزمية تحسين الفراشة (BOA)، تحسين سرب الأسد (LSO)، و تحسين ابن آوى الذهبي (GJO). وتمت مقارنة نتائج...



5 June 2026 in An International Journal of Optimization and Control: Theories & Applications (IJOCTA)
Verified
Journal Article
Open access
PDF file
HYHaolong Yang
Haolong Yang
QDQi Diao
Qi Diao
WCWeng Howe Chan
Weng Howe Chan
Kernel Extreme Learning Machine (KELM) is well-suited for nonlinear classification, but its performance is highly sensitive to the regularization parameter C and the RBF kernel width σ. To reduce manual tuning, we proposes a Snake Optimizer-based KELM model, termed SKELM, which jointly optimizes C and σ using validation accuracy as the fitness function. Experiments on ten UCI benchmark datasets indicate that compared with KELM, LSOKELM, and SSAKELM, SKELM achieves the unique best accuracy on five datasets and ties for the best accuracy on the remaining three datasets. The proposed method also shows fewer average iterations and a lower standard deviation under the current experimental setting. These results suggest that SKELM can serve as a effective parameter-search framework for KELM, although further validation with additional baselines, statistical tests, convergence curves, runtime comparisons, and more evaluation metrics remains necessary.

9 July 2021
Verified
Book Chapter
Closed access
PDF file
HYHaolong Yang
Haolong Yang
CHChunqiang Hu
Chunqiang Hu
QDQi Diao
Qi Diao

25 February 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
QDQi Diao
Qi Diao
WCWeng Howe Chan
Weng Howe Chan
AZAzlan Mohd Zain
Azlan Mohd Zain
KMKohbalan Moorthy
Kohbalan Moorthy
YCYiFan Chen
YiFan Chen
YHYuJie Huo
YuJie Huo
Automated X-ray security inspection requires object detectors to accurately and efficiently identify prohibited items under challenging conditions, such as dense occlusion, cluttered backgrounds, and limited computational resources. However, existing detectors often struggle with small, overlapping, or heavily occluded objects, which severely limits their real-world applicability. To address these challenges, we propose YOLOv8-DWConv-CSAF, a lightweight and discriminative multi-scale object detection framework specifically designed for X-ray imagery. Our method integrates architectural compression, attention-guided feature enhancement, and contrastive representation learning into a unified detection pipeline. Specifically, all standard convolutions in the YOLOv8 backbone are replaced with depthwise separable convolutions (DWConv), significantly reducing the number of parameters and computational cost while preserving representational capacity. To further enhance detection accuracy, we introduce a novel Channel-Spatial Attention Fusion (CSAF) module that synergistically combines SE and CBAM mechanisms to enrich both channel-wise and spatial feature representations. Additionally, stacked C2f modules facilitate effective multi-scale feature aggregation. To improve localization and class discriminability, we adopt a hybrid loss function that combines Pixel-wise IoU (PIoU) for precise bounding box regression with a supervised InfoNCE contrastive loss to promote intra-class compactness and inter-class separation in the learned feature space. Comprehensive evaluations on both the CLCXray and HiXray benchmarks validate that our model delivers state-of-the-art performance, combining high accuracy with real-time efficiency and robust generalization–making it well-suited for deployment in practical security screening systems.